Image de couverture de livre

Efficient Long-Document Reranking via Block-Level Embeddings and Top-k Interaction Refinement

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Li, Minghan, Gaussier, Eric, Zhou, Guodong
Format:	Preprint
Publié:	2025
Sujets:	Information Retrieval
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

EviRerank: Adaptive Evidence Construction for Long-Document LLM Reranking
par: Li, Minghan, et autres
Publié: (2024)

Domain Adaptation for Dense Retrieval and Conversational Dense Retrieval through Self-Supervision by Meticulous Pseudo-Relevance Labeling
par: Li, Minghan, et autres
Publié: (2024)

Retrieval-Feedback-Driven Distillation and Preference Alignment for Efficient LLM-based Query Expansion
par: Li, Minghan, et autres
Publié: (2026)

A Survey of Long-Document Retrieval in the PLM and LLM Era
par: Li, Minghan, et autres
Publié: (2025)

Unifying Multimodal Retrieval via Document Screenshot Embedding
par: Ma, Xueguang, et autres
Publié: (2024)

Efficient Listwise Reranking with Compressed Document Representations
par: Déjean, Hervé, et autres
Publié: (2026)

Automatic In-Domain Exemplar Construction and LLM-Based Refinement of Multi-LLM Expansions for Query Expansion
par: Li, Minghan, et autres
Publié: (2026)

Layer-wise Token Compression for Efficient Document Reranking
par: Zhuang, Shengyao, et autres
Publié: (2026)

Nemotron ColEmbed V2: Top-Performing Late Interaction Embedding Models for Visual Document Retrieval
par: Moreira, Gabriel de Souza P., et autres
Publié: (2026)

SumRank: Aligning Summarization Models for Long-Document Listwise Reranking
par: Feng, Jincheng, et autres
Publié: (2026)

Reranking with Compressed Document Representation
par: Déjean, Hervé, et autres
Publié: (2025)

GLIER: Generative Legal Inference and Evidence Ranking for Legal Case Retrieval
par: Li, Minghan, et autres
Publié: (2026)

Unbiased Multimodal Reranking for Long-Tail Short-Video Search
par: Xu, Wenyi, et autres
Publié: (2026)

Very Efficient Listwise Multimodal Reranking for Long Documents
par: Sun, Yiqun, et autres
Publié: (2026)

Whole-Pool Setwise Reranking with Long-Context Language Models
par: Li, Hang, et autres
Publié: (2026)

Leveraging Passage Embeddings for Efficient Listwise Reranking with Large Language Models
par: Liu, Qi, et autres
Publié: (2024)

An Efficient Framework for Whole-Page Reranking via Single-Modal Supervision
par: Zhang, Zishuai, et autres
Publié: (2025)

Stop Overthinking: Unlocking Efficient Listwise Reranking with Minimal Reasoning
par: Liu, Danyang, et autres
Publié: (2026)

S2G-RAG: Structured Sufficiency and Gap Judging for Iterative Retrieval-Augmented QA
par: Li, Minghan, et autres
Publié: (2026)

Dynamic Ranked List Truncation for Reranking Pipelines via LLM-generated Reference-Documents
par: Sinhababu, Nilanjan, et autres
Publié: (2026)

ToolRerank: Adaptive and Hierarchy-Aware Reranking for Tool Retrieval
par: Zheng, Yuanhang, et autres
Publié: (2024)

ICLERB: In-Context Learning Embedding and Reranker Benchmark
par: Ghossein, Marie Al, et autres
Publié: (2024)

Contextual Relevance and Adaptive Sampling for LLM-Based Document Reranking
par: Huang, Jerry, et autres
Publié: (2025)

LLM4Rerank: LLM-based Auto-Reranking Framework for Recommendations
par: Gao, Jingtong, et autres
Publié: (2024)

Efficient Top-k s-Biplexes Search over Large Bipartite Graphs
par: Xu, Zhenxiang, et autres
Publié: (2024)

Query Expansion in the Age of Pre-trained and Large Language Models: A Comprehensive Survey
par: Li, Minghan, et autres
Publié: (2025)

LURE-RAG: Lightweight Utility-driven Reranking for Efficient RAG
par: Chandra, Manish, et autres
Publié: (2026)

Next-Scale Generative Reranking: A Tree-based Generative Rerank Method at Meituan
par: Wang, Shuli, et autres
Publié: (2026)

RecRanker: Instruction Tuning Large Language Model as Ranker for Top-k Recommendation
par: Luo, Sichun, et autres
Publié: (2023)

Unbiased Top-k Learning to Rank with Causal Likelihood Decomposition
par: Zhao, Haiyuan, et autres
Publié: (2022)

$\mathbb{R}^{2k}$ is Theoretically Large Enough for Embedding-based Top-$k$ Retrieval
par: Wang, Zihao, et autres
Publié: (2026)

Denoising Neural Reranker for Recommender Systems
par: Mao, Wenyu, et autres
Publié: (2025)

DiffuRank: Effective Document Reranking with Diffusion Language Models
par: Liu, Qi, et autres
Publié: (2026)

Learning Refined Document Representations for Dense Retrieval via Deliberate Thinking
par: Ji, Yifan, et autres
Publié: (2025)

E2Rank: Your Text Embedding can Also be an Effective and Efficient Listwise Reranker
par: Liu, Qi, et autres
Publié: (2025)

On Listwise Reranking for Corpus Feedback
par: Yoon, Soyoung, et autres
Publié: (2025)

DeAR: Dual-Stage Document Reranking with Reasoning Agents via LLM Distillation
par: Abdallah, Abdelrahman, et autres
Publié: (2025)

Towards Storage-Efficient Visual Document Retrieval: An Empirical Study on Reducing Patch-Level Embeddings
par: Ma, Yubo, et autres
Publié: (2025)

UniRank: Unified List-wise Reranking via Confidence-Ordered Denoising
par: Jia, Pengyue, et autres
Publié: (2026)

Efficient Cold-Start Recommendation via BPE Token-Level Embedding Initialization with LLM
par: Zhao, Yushang, et autres
Publié: (2025)